593 citations · 1.8k across the 57 of their papers we have counts for
14 papers · 1 filter
NANO: A Unified Optimization Framework for Nonlinear Gaussian Filtering
Zhenxuan Ma, Haoning Wang, Wenhan Cao +1
Conventional Gaussian filtering typically approximates nonlinear models or their statistical moments and retains the Kalman update structure. The resulting approximation errors can…
Past, Future, All at Once: Mitigating Stability-Plasticity Dilemma via Post-hoc JANUS Rectification
Zhilong Zheng, Letian Tao, Yang Guan +7
Fine-tuning foundation models on new tasks inevitably suffer from catastrophic forgetting. While existing works attempt to mitigate this on the basis of parameter-efficient fine-tu…
Momentum as Residual-Driven Multiplier Correction for Deep Learning Optimization
Zhixin Ren, Yao Lyu, Congrong Li +2
Momentum-based optimizers are widely used in modern deep learning, yet the relations among momentum recursion, update geometry, and acceleration remain only partially understood. W…
Optimal copy complexity of quantum state cloning
Sangwoo Jeon, Vaughn Sohn, Changhun Oh
Quantum state cloning is the task of approximately producing additional copies of an unknown quantum state from a finite number of input copies. The optimal cloning fidelity is kno…
On the Identifiability of Controlled World Models
Xiangteng Zhang, Yang Guan, Bo Zhang +3
World model serves as a promising tool to infer environment dynamics under high-dimensional observations and candidate actions. Recently, LeCun's JEPA provides a compelling framewo…
Distributional Soft Bellman Operator under the Cramér Geometry
Keru Wang, Yixin Deng, Yao Lyu +2
Distributional soft policy iteration (DSPI) provides an important framework for combining distributional reinforcement learning (DRL) with maximum-entropy control, in which the pol…
FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving
Bonan Wang, Letian Tao, Bin Shuai +7
Deep reinforcement learning is pivotal for closed-loop autonomous driving yet remains constrained by severe bottlenecks in sampling efficiency. Standard parallel sampling mitigates…
Factor-Aware Mixture-of-Experts with Pretrained Encoder for Combinatorial Generalization
Feihong Zhang, Guojian Zhan, Zeyu He +8
The integration of pretrained encoders with diffusion policies has become a dominant paradigm for visual robotic manipulation. However, it still struggles to generalize across comp…
World Engine: Towards the Era of Post-Training for Autonomous Driving
Tianyu Li, Li Chen, Caojun Wang +16
Autonomous vehicles must operate safely in the real world, where errors can have severe consequences. Although modern end-to-end driving policies excel in routine scenarios, their…
M3imic: Learning a Versatile Whole-Body Controller for Multimodal Motion Mimicking
Zuxing Lu, Ziang Zheng, Yao Lyu +7
Building a general-purpose whole-body controller is essential for enabling diverse motion capabilities in humanoid robots across a wide range of downstream tasks, including locomot…
FUSE: A Framework for Unified State Estimation in Vehicular and Robotic SLAM Systems
Wei Wu, Honglin Chen, Wenhan Cao +7
Tightly coupled SLAM formulations under mixed-rate sensing often bind temporal processing, local geometric association, estimator formulation, and map-update policy into method-spe…
Towards Physically Consistent 4D Scene Reconstruction for Closed-loop Autonomous Driving Simulation
Bowyn Tan, Yutong Xie, Bai Huang +5
High-fidelity street scene reconstruction is pivotal for end-to-end autonomous driving simulation, where novel-view synthesis (NVS) and time-varying information modeling are two fu…
On the Equilibrium between Feasible Zone and Uncertain Model in Safe Exploration
Yujie Yang, Zhilong Zheng, Shengbo Eben Li
Ensuring the safety of environmental exploration is a critical problem in reinforcement learning (RL). While limiting exploration to a feasible zone has become widely accepted as a…
STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
Shiqi Liu, Zeyu He, Guojian Zhan +10
Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic techniques such as entropy regu…